Experience and learning path of introductory deep learning and machine learning

Click on the above “ Xiaobai studies vision ”, Optional plus " Star standard " or “ Roof placement ”

 Heavy dry goods , First time delivery 

author ：Caliber（ Tsinghua University Ph.D. in Applied Mathematics ）

link ：https://zhuanlan.zhihu.com/p/150507220

Reprinted from ： Deep learning algorithm and computer vision

It has been some time since I came into contact with deep learning and machine learning , He is also a junior alchemy player , Just want to share some experiences and learning paths on how to get started with machine learning and deep learning .

Preparatory work ：

1. A persistent heart ( That's the most important thing )

2. Learn to solve your own problems by searching ( Most of the problems encountered in the process of learning can be solved by searching )

3. Mathematical basis ： Advanced mathematics 、 linear algebra 、 Probability theory and mathematical statistics and A little bit of optimization

4. A computer ( It's better to have GPU), If conditions permit , It is also necessary to have one equipped with GPU Server for

With all this , We can start downloading and installing the software .

Recommended Anaconda3+Pycharm

The download address is as follows ：https://www.anaconda.com/products/individual

https://www.jetbrains.com/pycharm/download/

Generally beginners download the community version , namely Community that will do .

About download, installation and basic configuration , Not here , Here is the first step to develop your retrieval ability , The network has a lot of information to tell you how to install and configure .

Recommended at the beginning Jupyter&Spyder, After you are familiar with large projects, you can start to use Pycharm 了 .

Now the basic preparations are ready . You can start learning .

The first is python Basic learning , What I personally recommend here is Python Basic and data analysis . The basic learning path is as follows ：

python Basics

Don't worry about it first python Basic teaching video , Very friendly and basic .

https://www.bilibili.com/video/BV1wW411Y7ai

Speaking of the video foundation just now, the implication is that it is not enough , The following videos are recommended ： utilize python Do data analysis https://urlify.cn/JV7NBr

It's a video of a Taiwanese teacher , The explanation was very detailed , But a little bit longer .

machine learning

After learning the above two videos , You already have a good python Basic programming . Now we can formally enter the learning process of machine learning .

The recommended learning paths are as follows ：

Go to see Mr. Li Hang's 《 Statistical learning method 》 And use it with the code （ Code in github It should be very easy to find ）

The above process should be difficult , Because there are a lot of mathematical derivations , After understanding these mathematical derivations , Combined with code and specific examples , The harvest will be more .

Deep learning and actual combat

After finishing the traditional machine learning , You can formally enter the deep learning process ：

My advice here is , Learn relevant basic knowledge first , Then enter the actual combat link .

This is because I personally use Pytorch Framework , Just talk about Pytorch Learn from it. . If the children's shoes can reach this step according to my learning method , How to learn Pytorch There should be no need for me to say more . I would like to recommend some learning materials other than official documents .

First of all Github The last highly praised document written by a Korean ：

https://github.com/yunjey/pytorch-tutorial

The code inside is very elegant , It also contains some classic models , It is well worth reading , Run a run .

Another learning material I highly recommend is Hands on learning and deep learning pytorch edition , It is divided into implementation from scratch and adoption Pytorch Realize two parts , Both theory and practice are taken into account .

https://tangshusen.me/Dive-into-DL-PyTorch/#/

Finally, I recommend a video about actual combat , It's online in July , stay B On the station , I hang it here ( I don't know if it will infringe , If there is infringement , Please contact me to delete ).https://urlify.cn/bqYRNr

This video focuses on NLP field , There are also some. CV Of . Here is another post about CV Live video of , But it seems to be TF Framework of the , About CV Chinese for pytorch I haven't found anything good in the video , Let's keep it here for the time being , The English video strongly recommends Stanford CS231.https://urlify.cn/ZNrUNr

Let's just write something like this for the time being , Completed the above , Is already a junior alchemy player , What to read the paper , You can start with the actual projects , Do it yourself more , Think more , It must be improved gradually , Share with you ！

The good news ！

Xiaobai learns visual knowledge about the planet

Open to the outside world

 download 1：OpenCV-Contrib Chinese version of extension module 

 stay 「 Xiaobai studies vision 」 Official account back office reply ： Extension module Chinese course , You can download the first copy of the whole network OpenCV Extension module tutorial Chinese version , Cover expansion module installation 、SFM Algorithm 、 Stereo vision 、 Target tracking 、 Biological vision 、 Super resolution processing and other more than 20 chapters .


 download 2：Python Visual combat project 52 speak 
 stay 「 Xiaobai studies vision 」 Official account back office reply ：Python Visual combat project , You can download, including image segmentation 、 Mask detection 、 Lane line detection 、 Vehicle count 、 Add Eyeliner 、 License plate recognition 、 Character recognition 、 Emotional tests 、 Text content extraction 、 Face recognition, etc 31 A visual combat project , Help fast school computer vision .


 download 3：OpenCV Actual project 20 speak 
 stay 「 Xiaobai studies vision 」 Official account back office reply ：OpenCV Actual project 20 speak , You can download the 20 Based on OpenCV Realization 20 A real project , Realization OpenCV Learn advanced .


 Communication group 

 Welcome to join the official account reader group to communicate with your colleagues , There are SLAM、 3 d visual 、 sensor 、 Autopilot 、 Computational photography 、 testing 、 Division 、 distinguish 、 Medical imaging 、GAN、 Wechat groups such as algorithm competition （ It will be subdivided gradually in the future ）, Please scan the following micro signal clustering , remarks ：” nickname + School / company + Research direction “, for example ：” Zhang San  +  Shanghai Jiaotong University  +  Vision SLAM“. Please note... According to the format , Otherwise, it will not pass . After successful addition, they will be invited to relevant wechat groups according to the research direction . Please do not send ads in the group , Or you'll be invited out , Thanks for your understanding ~